Hybrid Intra-hour Solar PV Power Forecasting using Statistical and Skycam-based Methods

We propose and test a hybrid solar PV power forecasting model which optimally combines statistical and skycam-based forecasts. We show our model's capability to produce accurate forecasts seamlessly from 10-s to 10-min ahead using high-frequency measurements in Canberra, Australia. The hybrid model relies on an empirical clear-sky model for solar power and the identification of three condition variables, which are able to separate and model characteristic events associated with them. It significantly overperforms both its statistical component and its skycam component alone, achieving a relative RMSE reduction (forecast skill) of 19% against persistence of clear-sky index at 5-min ahead.